© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34691
    Prev
    Next
    INDEX
    Explanations

    names starting with Schm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nearly
    -0.85
     bro
    -0.81
     almost
    -0.78
     hampir
    -0.78
    catalog
    -0.76
     good
    -0.75
    cides
    -0.74
     strong
    -0.73
     no
    -0.73
     often
    -0.70
    POSITIVE LOGITS
    猜测
    0.82
    despite
    0.79
     déta
    0.77
    worse
    0.77
     Hearst
    0.73
    タコ
    0.73
    ガネ
    0.72
    obviously
    0.72
     rév
    0.71
     SPECIFIC
    0.71
    Activations Density 0.011%

    No Known Activations